haive.agents.reasoning_and_critique.reflexion.agent
===================================================

.. py:module:: haive.agents.reasoning_and_critique.reflexion.agent

.. autoapi-nested-parse::

   Reflexion agent.

   Composes ReactAgent (draft/revise with optional tools) and SimpleAgent
   (reflection/grading with structured output) in an iterative improvement loop.

   Graph: START -> draft_answer -> reflect_answer -> [should_continue] -> revise_answer -> reflect_answer -> ... -> finish_answer -> END

   The drafter and reflector are real haive agents (ReactAgent, SimpleAgent)
   that use our tested infrastructure for LLM calls, tool use, and structured output.



Classes
-------

.. autoapisummary::

   haive.agents.reasoning_and_critique.reflexion.agent.ReflexionAgent


Functions
---------

.. autoapisummary::

   haive.agents.reasoning_and_critique.reflexion.agent.create_reflexion_agent


Module Contents
---------------

.. py:class:: ReflexionAgent

   Bases: :py:obj:`haive.agents.base.agent.Agent`


   Reflexion: iterative draft-reflect-revise using ReactAgent + SimpleAgent.

   - Drafter: ReactAgent with optional tools for initial answer + revisions
   - Reflector: SimpleAgent with structured output (Reflection model)
   - Loop: draft -> reflect -> revise -> reflect -> ... until max_iterations


   .. py:method:: build_graph()

      Build the Reflexion graph.

      Flow: START -> draft_answer -> reflect_answer -> [revise_answer | finish_answer]
                                                          |               |
                                                          v               v
                                                     reflect_answer      END



   .. py:method:: compile(**kwargs)

      Compile: build agents lazily, use BaseGraph.to_langgraph().



   .. py:method:: get_answer(result)

      Extract the final answer from a run result.



   .. py:method:: run(input_data, **kwargs)

      Run reflexion. Accepts a string query or a dict with 'input' key.



.. py:function:: create_reflexion_agent(tools=None, model='gpt-4o-mini', **kwargs)

   Factory for ReflexionAgent.